Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1973 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1611396 (Python Code)

Max Activating Token Index: 464

Text #1

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1629641 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7921. Min Act: -0.0001

Data Index: 1560904 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1625099 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7879. Min Act: -0.0001

Data Index: 1588194 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7591. Min Act: -0.0001

Data Index: 1504590 (Python Code)

Max Activating Token Index: 1010

Text #6

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.8022. Min Act: -0.0001

Data Index: 1274355 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7314. Min Act: -0.0001

Data Index: 1435424 (Python Code)

Max Activating Token Index: 788

Text #8

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7435. Min Act: -0.0001

Data Index: 247568 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1588885 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7424. Min Act: -0.0001

Data Index: 1559185 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1507154 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7611. Min Act: -0.0001

Data Index: 1640343 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7424. Min Act: -0.0001

Data Index: 1414330 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1370066 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1626502 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1534069 (Python Code)

Max Activating Token Index: 725

Text #17

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7285. Min Act: -0.0001

Data Index: 1609215 (Python Code)

Max Activating Token Index: 973

Text #18

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7770. Min Act: -0.0001

Data Index: 1537094 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.7279. Min Act: -0.0001

Data Index: 1062129 (C4 (Web Text))

Max Activating Token Index: 932